@inproceedings{wang-etal-2024-pruning,
    title = "Pruning before Fine-tuning: A Retraining-free Compression Framework for Pre-trained Language Models",
    author = "Wang, Pingjie  and
      Liu, Hongcheng  and
      Wang, Yanfeng  and
      Wang, Yu",
    editor = "Calzolari, Nicoletta  and
      Kan, Min-Yen  and
      Hoste, Veronique  and
      Lenci, Alessandro  and
      Sakti, Sakriani  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://preview.aclanthology.org/corrections-2025-06/2024.lrec-main.1162/",
    pages = "13279--13289",
    abstract = "Structured pruning is an effective technique for compressing pre-trained language models (PLMs), reducing model size and improving inference speed for efficient deployment. However, most of existing pruning algorithms require retraining, leading to additional computational overhead. While some retraining-free approaches have been proposed for classification tasks, they still require a fully fine-tuned model for the task, and may cause catastrophic performance degradation on generative tasks. To address these challenges, we propose P-pruning (pre-pruning), an innovative task-specific compression framework. P-pruning prunes redundant modules of PLMs before fine-tuning, reducing the costs associated with fine-tuning. We also introduce a pruning algorithm for this framework, which includes two techniques: (1) module clustering, which clusters the outputs of all heads and neurons based on the task input; and (2) centroid selection, which identifies the most salient element in each cluster and prunes the others. We apply our method to BERT and GPT-2 and evaluate its effectiveness on GLUE, SQuAD, WikiText-2, WikiText-103, and PTB datasets. Experimental results demonstrate that our approach achieves higher performance in both classification and generative tasks, while also reducing the time required for fine-tuning."
}